The large difference between processor CPU cycle time and memory access time, often referred to as the memory wall, severely limits the performance of streaming applications. Some data centers have shown servers being idle three out of four clocks. High performance instruction sequenced systems are not energy efficient. The execute stage of even simple pipeline processors only use 9% of the pipeline's total energy. A hybrid dataflow system within a memory module is shown to have 7.2 times the performance with 368 times better energy efficiency than an Intel Xeon server processor on the analyzed benchmarks. The dataflow implementation exploits the inherent parallelism and pipelining of the application to improve performance without the overhead functions of caching, instruction fetch, instruction decode, instruction scheduling, reorder buffers, and speculative execution used by high performance out-of-order processors. Coarse grain reconfigurable logic in an energy efficient silicon process provides flexibility to implement multiple algorithms in a low energy solution. Integrating the logic within a 3D stacked memory module provides lower latency and higher bandwidth access to memory while operating independently from the host system processor.

Modern database systems have to process huge amounts of data and should provide results with low latency at the same time. To achieve this, data is nowadays typically hold completely in main memory, to benefit of its high bandwidth and low access latency that could never be reached with disks. Current in-memory databases are usually columnstores that exchange columns or vectors between operators and suffer from a high tuple reconstruction overhead. In this paper, we present the indexed table-at-a-time processing model that makes indexes the first-class citizen of the database system. The processing model comprises the concepts of intermediate indexed tables and cooperative operators, which make indexes the common data exchange format between plan operators. To keep the intermediate index materialization costs low, we employ optimized prefix trees that offer a balanced read/write performance. The indexed tableat-a-time processing model allows the efficient construction of composed operators like the multi-way-select-join-group. Such operators speed up the processing of complex OLAP queries so that our approach outperforms state-of-the-art in-memory databases.

Den här studien handlar om att undersöka värmemotståndet för ett vattenrutschbaneelement för att se om det finns en skillnad mellan schablonmässiga och uppmätta värden för värmekonduktiviteten hos materialen men även undersöka hur stor påverkan de längsgåendeflänsarna har på transmissionsförlusten. Det finns ofta en skillnad mellan det schablonmässiga och faktiska värden när matningar genomförs på färdigställda konstruktioner. Syftet med studien är att undersöka riktigheten av schablonmässigt bestämt värmemotståndet för ett vattenrutschbaneelement (banmodell typ-1000) som produceras av Hydro Sport AB. Studien kommer även att undersöka materialens temperaturberoende utifrån värmekonduktivitet. En laboratoriemätning utfördes i ett klimatkammarskåp med värmeflödesmätare och termoelement för att bestämma värmekonduktiviteten för glasfiberlaminatet (GFRP) och mäta värmemotståndet för den sammansatta konstruktionen och genom att subtrahera glasfiberlaminatet värmemotstånd för att erhålla värmekonduktiviteten för Armaflex isoleringen. De framtagna värmekonduktiviteterna användes som parametrar i Comsol Multiphysics simuleringarna för att undersöka hur stor skillnad schablonmässiga och uppmätta värden har för denna specifika vattenrutschbana. Handberäkningar gjordes för att säkerställa att Comsol Multiphysics simuleringarna var pålitliga. Resultaten som framtagits i studien visar på att båda materialen men framför allt glasfiberlaminatet hade ett lägre värmekonduktivitetsvärde än det schablonmässiga som används i beräkningar i dagsläget. / This study is about examining the thermal resistance of a water slide element to see if it’s a difference between standard values and measured values for the materials thermal conductivity and also see how big an impact the horizontal flanges have for the heat balance of the structure. There is often a difference between the theoretical and actual values that is measured when the construction is finished.The purpose of this study is to validate the accuracy of the thermal resistance of a water slide element (track model typ-1000) that is produced by Hydro Sport AB. This study also covers thermal conductivity temperature dependent for the materials. A laboratory measurement was performed in a climate chamber with heat flux meters and thermocouples to obtain the thermal conductivity for the glass fibre reinforced polymer (GFRP) and measure the heat resistance for the whole composite construction and from there substract the GFRP heat resistance to obtain the thermal conductivity for the Armaflex insulation. The obtained thermal conductivity was used as parameters for the simulations in Comsol Multiphysics to investigate how big the impacts are between standard values and measured for this particular water slide type. To make sure that the Comsol Multiphysics simulations were trustworthy a hand calculation was made for this purpose.The results in this study revealed that both materials but especially GFRP had a better thermal conductivity than the standard value that is used today.

This project is a master’s thesis in Industrial Design that has been conducted in the spring of 2022 at Luleå University of Technology. The project is a cooperation with the company Neava and is about improving their online tool Design Studio. The goal of the project is to improve the online tool from an environmentally friendly perspective, i.e., how information is presented regarding material’s impact on the environment and how energy efficient the house will be when all the choices have been made.  Today, there are two different interfaces of Design Studio. One that is based on specific requirements from a customer, and another that is designed for sellers. None of these interfaces provides the user with information about how the materials are affecting the environment. Today it is important to think about the materials and energy efficiency when new houses are being built to create a sustainable future.  The work has been conducted by the process Design Thinking, which is an iterative process that is performed in five different phases: empathize, define, ideate, prototype, and test. In the first phase, an understanding of the user was created, this was conducted through interviews and a survey. In the second phase, the user was identified, and user needs were established. In the third phase, different ideas and concepts were generated and then evaluated by users. In the fourth phase, a clickable prototype was created in the program Adobe XD. In the fifth phase, the prototype was tested on users and later improved based on the results.  The final result is a clickable prototype that informs the user about the available materials and how they are affecting the environment. The materials are categorized into three different groups: red, yellow, and green. If a material is in the red category, it indicates that the material is the worst for the environment. If a material is in the yellow category, it indicates that the material is okay for the environment. If a material is in the green category, it indicates that the material is the best for the environment. These three colors are connected to the environmental meter, the indicator shows the user how environmentally friendly materials the user has selected and how energy efficient the house will be.

<p>Spiking Neural Networks (SNNs) have recently attracted significant research interest as the third generation of artificial neural networks that can enable low-power event-driven data analytics. We propose ANN-SNN conversion using “soft re-set” spiking neuron model, referred to as Residual Membrane Potential (RMP) spiking neuron, which retains the “resid- ual” membrane potential above threshold at the firing instants. In addition, we propose a time-based coding scheme, named Temporal-Switch-Coding (TSC), and a corresponding TSC spiking neuron model. Each input image pixel is presented using two spikes with opposite polarity and the timing between the two spiking instants is proportional to the pixel intensity. We demonstrate near loss-less ANN-SNN conversion using RMP neurons for VGG-16, ResNet-20, and ResNet-34 SNNs on challenging datasets including CIFAR-10, CIFAR-100, and ImageNet. With the help of TSC coding, it achieves 7-14.5× less inference latency, and 30-60× fewer addition operations and memory accesses per inference across datasets compared to the state of the art (SOTA) SNN models. In the second part of the thesis, we propose a new type of recurrent neural network (RNN) architecture, named Os- cillatory Fourier Neural Network (O-FNN). We demonstrate that O-FNN is mathematically equivalent to a simplified form of Discrete Fourier Transform applied onto periodical activa- tion. In particular, the computationally intensive back-propagation through time in training is eliminated, leading to faster training while achieving the SOTA inference accuracy in a diverse group of sequential tasks. For instance, applying the proposed model to sentiment analysis on IMDB review dataset reaches 89.4% test accuracy within 5 epochs, accompanied by over 35x reduction in the model size compared to Long Short-Term Memory (LSTM). The proposed novel RNN architecture is well poised for intelligent sequential processing in resource constrained hardware.</p>

Technology is developing fast, and more smart devices are being implemented in our everyday life. Internet of Things (IoT) is a modern technology where physical objects are embedded with sensors in order for them to communicate. IoT can help reduce energy consumption in households, yet usage of such technologies is not widespread. There is a gap in the understanding of why the adoption of IoT technologies is lagging behind expectations. In this concept, energy-efficient IoT devices include smart devices that can help reduce energy wastage by efficient management of energy consumption. The aim of this study is to better understand the challenges of energy-efficient IoT implementation in Swedish home environments. This research explores Swedish customers' awareness of, attitude towards and experiences with IoT devices that reduce energy wastage, in order to assess barriers to adoption. To understand the challenges of IoT adoption in Swedish households, a mixed-method case study was conducted. Data was collected using a combination of interviews, surveys, and reviews from websites and forums, with eight people being interviewed, 26 people responding to the survey, and 302 reviews included as a secondary source of information. The collected data were analysed with thematic analysis and descriptive statistics.The analysis presents evidence that factors such as social and mass media influence, lack of information, compatibility and connectivity challenges, lack of standardisation, high cost, distrust, and high expectation contribute to the reluctance of energy-efficient IoT adoption. Widespread adoption of energy-efficient IoT devices can be achieved by facilitating knowledge dissemination in mass media, providing information transparency, enabling cross-platform interoperability and providing adequate support.

Between year 1961 and 1975 were about one million homes produced, which today is called the million programme. These homes are now in a great need of renovation as they contain hazardous substances in the materials, unnecessarily high energy use and they are in critical technical condition. Purpose: of the degree project is to identify how we can become increasingly sustainable in ROT-projects within the million programme areas. The degree projects studies among other things how a renovation will be sustainable, materials and waste impact, about the million programme rebuilding needs and rebuilding needs of low-energy houses in the million programme. The method: The degree project is based on a literature study, a questionnaire study and an interview study. The literature study has been carried out to gain an increased knowledge of how a ROT-project works and facts about the million programme. The survey consisted of questions about what the environmental work looks like in various ROT-projects. Entrepreneurs working on ROT-projects, landlords who manage housing in the million programme and tenants who live in the million programmehave participated in the survey. An interview study has been conducted with various ROT-entrepreneurs and landlords to get an overview of how the work of the million programmehas looked environmentally. The result: The million programme leak large amounts of energy and heat. Older have shown that greenhouse gas emissions and energy use have increased, so the need for renovation is becoming more apparent. Sustainable renovation is needed to reduce the negative environmental impact of greenhouse gas emissions and energy gas. In a construction process does material production have a major impact on the environment. When it comes to material selection and waste management is an important aspect for the environment within a ROT-project. In order to be able to work in an environmentally friendly way, it is necessary to plan in detail about various factors when handling the use of materials. The various factors are inventory, waste sorting, ordering materials in the right dimension, choosing materials with regard to the environment and handling the materials well during the construction process. Conclusion: The million programme homes are energyintesive and require among other things trunk replacement, ventilation replacement, replacement of electrical installations, windows, balconies and facades. In order to renovate the million programme homes good knowledge is required about ay hazardous substances in the materials and what measures are required to make the homes more energy efficient.

京都大学 / 0048 / 新制・課程博士 / 博士(情報学) / 甲第20778号 / 情博第658号 / 新制||情報||113(附属図書館) / 京都大学大学院情報学研究科通信情報システム専攻 / (主査)教授 小野寺 秀俊, 教授 佐藤 高史, 教授 黒橋 禎夫 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

<p>Next-generation (Next-Gen) mobile applications, Extended Reality (XR), which encompasses Virtual/Augmented/Mixed Reality (VR/AR/MR), promise to revolutionize how people interact with technology and the world, ushering in a new era of immersive experiences. However, the hardware capacity of mobile devices will not grow proportionally with the escalating resource demands of the mobile apps due to their battery constraint. To bridge the gap, edge computing has emerged as a promising approach. It is further boosted by emerging 5G cellular networks, which promise low latency and high bandwidth. However, realizing the full potential of edge computing faces several fundamental challenges.</p> <p><br></p> <p>In this thesis, we first discuss a set of fundamental design challenges in supporting Next-Gen mobile applications via edge computing. These challenges extend across the three key system components involved — mobile clients, edge servers, and cellular networks. We then present how we address several of these challenges, including (1) how to coordinate mobile clients and edge servers to achieve stringent QoE requirements for Next-Gen apps; (2) how to optimize energy consumption of running Next-Gen apps on mobile devices to ensure long-lasting user experience; and (3) how to model and generate control-plane traffic of cellular networks to enable innovation on mobile network architectural design to support Next-Gen apps not only over 4G but also over 5G and beyond.</p> <p><br></p> <p>First, we present how to optimize the latency in edge-assisted XR system via the mobile-client and edge-server co-design. Specifically, we exploit key insights about frame similarity in VR to build the first multiplayer edge-assisted VR design, Coterie. We demonstrate that compared with the prior work on single-player VR, Coterie reduces the per-player network load by 10.6X−25.7X, and can easily support 4 players for high-quality VR apps on Pixel 2 over 802.11ac running at 60 FPS and under 16ms responsiveness without exhausting the finite wireless bandwidth.</p> <p><br></p> <p>Second, we focus on the energy perspective of running Next-Gen apps on mobile devices. We study a major limitation of a classic and de facto app energy management technique, reactive energy-aware app adaptation, which was first proposed two decades ago. We propose, design, and validate a new solution, the first proactive energy-aware app adaptation, that effectively tackles the limitation and achieves higher app QoE while meeting a given energy drain target. Compared with traditional approaches, our proactive solution improves the QoE by 44.8% (Pixel 2) and 19.2% (Moto Z3) under low power budget.</p> <p><br></p> <p>Finally, we delve into the third system component, cellular networks. To facilitate innovation in mobile network architecture to better support Next-Gen apps, we characterize and model the control-plane traffic of cellular networks, which has been mostly overlooked by prior work. To model the control-plane traffic, we first prove that traditional probability distributions that have been widely used for modeling Internet traffic (e.g., Poisson, Pareto, and Weibull) cannot model the control-plane traffic due to the much higher burstiness and longer tails in the cumulative distributions of the control-plane traffic. We then propose a two-level state-machine-based traffic model based on the Semi-Markov model. We finally validate that the synthesized traces by using our model achieve small differences compared with the real traces, i.e., within 1.7%, 4.9% and 0.8%, for phones, connected cars, and tablets, respectively. We also show that our model can be easily adjusted from LTE to 5G, enabling further research on control-plane design and optimization for 4G/5G and beyond.</p>

Purpose: this degree project investigates the homeowner’s knowledge about their energy use and the impact of using visualisation tools such as thermal imaging to enhance public engagement in energy conservation in building. Additionally, the study try to increase the understanding of how people's behavior affects the energy use in buildings. The method: the presented study is based on 12 participants who own a single-family house in central Sweden. Participation in this study involved responding to two questionnaires and conducting a thermography inspection. A methodology developed to replace a standard thermography inspection with a DIY themography survey. The study identified and filled the gap in the literature, by allowing house owners to carry out the thermographing inspection of their own buildings, free of charge and by themselves. The participants took part of a developed educational material that helps in increasing energy awareness and includes explanations about how to interpret the thermal images and provides suggestions for possible conservation measures. Finally, a data analyse carried out based on questionnairs, thermal images and communications with the house owners. The results: cold bridges are the most common cause of heat loss in the inspected single-family houses. Householders with older buildings who have long term plan to live in their building are willing to implement measures, while participants with newer buildings do not consider it as necessary. The infrared camera has been an effective tool for visualization of heat loss and attract attention. Many participants are surprised over the results. Conclusion: the study confirms that the infrared camera is an effective tool for heat loss visualization and can be used for enhancing public engagement in energy conservation in building. Thanks to this visualization, Swedish homeowners have gained an increased interest in energy-efficient measures such as additional insulation, window replacement and sun protection. The study has increased the general awareness and knowledge regarding energy efficiency in buildings.